<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (Vaguery)</title>
    <link>https://pinboard.in/u:Vaguery/public/</link>
    <description>recent bookmarks from Vaguery</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://arxiv.org/abs/2512.06522v2"/>
	<rdf:li rdf:resource="https://pubs.aip.org/aip/cha/article/35/8/083124/3358770/Hierarchical-clustering-in-mean-field-coupled"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2107.08013"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2210.02753"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2202.09179"/>
	<rdf:li rdf:resource="https://aclanthology.org/2022.findings-acl.81/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.08995"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1808.05689"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2001.08372"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2103.06040"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.03972"/>
	<rdf:li rdf:resource="http://astrobiology.com/2021/04/inferring-exoplanet-disequilibria-with-multivariate-information-in-atmospheric-reaction-networks.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1807.06414"/>
	<rdf:li rdf:resource="http://proceedings.mlr.press/v54/hong17a.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1602.04181"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1808.05740"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1510.00850"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.08237"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.01910"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.04816"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.06912"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1809.02786"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1902.01023"/>
	<rdf:li rdf:resource="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5411762/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1704.00454"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1512.04349"/>
	<rdf:li rdf:resource="http://www.pnas.org/content/early/2018/08/28/1810575115"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.00222"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.04594"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1802.03426"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1404.1008"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1604.03159"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.07797"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.07321"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1507.03067"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1703.04823"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1704.00794"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1608.03544"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1501.01822"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1603.06252"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1606.07312"/>
	<rdf:li rdf:resource="http://www.nature.com/nmeth/journal/v12/n3/abs/nmeth.3254.html"/>
	<rdf:li rdf:resource="http://www.sciencedirect.com/science/article/pii/S1751157712001034"/>
	<rdf:li rdf:resource="http://ieeexplore.ieee.org/abstract/document/5589222/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.02808"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1506.07613"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1607.06407"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1607.06294"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.05579"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1512.06809"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1607.06318"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1605.00562"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1511.05933"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1605.07030"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1606.00985"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1602.02514"/>
	<rdf:li rdf:resource="https://papers.nips.cc/paper/5991-differentially-private-subspace-clustering"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1507.01555"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1511.01964"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1505.05740"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1508.01057"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1412.7012"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1510.00012"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1310.4945"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1508.04887"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1412.1947"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1412.5902"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1309.6895"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1505.03934"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1506.08977"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://arxiv.org/abs/2512.06522v2">
    <title>[2512.06522v2] Hierarchical Clustering With Confidence</title>
    <dc:date>2026-05-23T12:01:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2512.06522v2</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Agglomerative hierarchical clustering is one of the most widely used approaches for exploring how observations in a dataset relate to each other. However, its greedy nature makes it highly sensitive to small perturbations in the data, often producing different clustering results and making it difficult to separate genuine structure from spurious patterns. In this paper, we show how randomizing hierarchical clustering can be useful not just for measuring stability but also for designing valid hypothesis testing procedures based on the clustering results.
We propose a simple randomization scheme together with a method for constructing a valid p-value at each node of the hierarchical clustering dendrogram that quantifies evidence against performing the greedy merge. Our test controls the Type I error rate, works with any hierarchical linkage without case-specific derivations, and simulations show it is substantially more powerful than existing selective inference approaches. To demonstrate the practical utility of our p-values, we develop an adaptive α-spending procedure that estimates the number of clusters, with a probabilistic guarantee on overestimation. Experiments on simulated and real data show that this estimate yields powerful clustering and can be used, for example, to assess clustering stability across multiple runs of the randomized algorithm.
]]></description>
<dc:subject>clustering statistics numerical-methods probability-theory unsupervised-learning algorithms rather-interesting to-write-about to-cite consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a39717e23952/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unsupervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-cite"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://pubs.aip.org/aip/cha/article/35/8/083124/3358770/Hierarchical-clustering-in-mean-field-coupled">
    <title>Hierarchical clustering in mean-field coupled Stuart–Landau oscillators | Chaos: An Interdisciplinary Journal of Nonlinear Science | AIP Publishing</title>
    <dc:date>2025-08-22T12:49:38+00:00</dc:date>
    <link>https://pubs.aip.org/aip/cha/article/35/8/083124/3358770/Hierarchical-clustering-in-mean-field-coupled</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Clustered solutions in oscillator networks provide an important insight into how a system might diversify from a synchronous solution into spatiotemporal complex solutions. They can, therefore, form a link between the fully synchronized and incoherent states. Despite their fundamental role in coupled oscillator dynamics, our understanding of how these clusters form and differentiate is still quite limited. Here, we study an ensemble of globally coupled Stuart–Landau oscillators and focus on how 3-cluster solutions emerge from 2-cluster solutions and how the different 3-cluster solutions are organized in parameter space. We show that the arrangement of the clusters is dictated by a codimension-two point, which we call a Type-II cluster singularity. Furthermore, our study points to a hierarchical structure of multi-cluster solutions.

]]></description>
<dc:subject>coupled-oscillators nonlinear-dynamics clustering rather-interesting to-understand to-simulate consider:non-oscillatory-entrainment phase-transitions edge-of-chaos</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e54d1cd135a1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:coupled-oscillators"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:non-oscillatory-entrainment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:phase-transitions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:edge-of-chaos"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2107.08013">
    <title>[2107.08013] Machine learning of Kondo physics using variational autoencoders and symbolic regression</title>
    <dc:date>2024-07-10T13:41:50+00:00</dc:date>
    <link>https://arxiv.org/abs/2107.08013</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We employ variational autoencoders to extract physical insight from a dataset of one-particle Anderson impurity model spectral functions. Autoencoders are trained to find a low-dimensional, latent space representation that faithfully characterizes each element of the training set, as measured by a reconstruction error. Variational autoencoders, a probabilistic generalization of standard autoencoders, further condition the learned latent space to promote highly interpretable features. In our study, we find that the learned latent variables strongly correlate with well known, but nontrivial, parameters that characterize emergent behaviors in the Anderson impurity model. In particular, one latent variable correlates with particle-hole asymmetry, while another is in near one-to-one correspondence with the Kondo temperature, a dynamically generated low-energy scale in the impurity model. Using symbolic regression, we model this variable as a function of the known bare physical input parameters and "rediscover" the non-perturbative formula for the Kondo temperature. The machine learning pipeline we develop suggests a general purpose approach which opens opportunities to discover new domain knowledge in other physical systems.
]]></description>
<dc:subject>materials-science learning-from-data genetic-programming symbolic-regression machine-learning rather-interesting clustering pattern-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:af6a41ae0e59/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:materials-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-from-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pattern-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2210.02753">
    <title>[2210.02753] Communities as Vague Operators: Epistemological Questions for a Critical Heuristics of Community Detection Algorithms</title>
    <dc:date>2023-05-21T12:25:38+00:00</dc:date>
    <link>https://arxiv.org/abs/2210.02753</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this article, we aim to analyse the nature and epistemic consequences of what figures in network science as patterns of nodes and edges called 'communities'. Tracing these as multi-faceted and ambivalent, we propose to describe the concept of community as a 'vague operator' related to Susan Leigh Star's notion of the boundary object but more loose, like a collection of hints, and propose that the ability to construct different modes of faceting that are both vague and hyper-precise, in semiotic, technical and social terms is core both to digital politics and the analysis of 'communities'. Engaging with these formations in terms drawn from mathematics and software studies enables a wider mapping of their formation. Disentangling different lineages in network science then allows us to contextualise the founding account of 'community' popularised by Michelle Girvan and Mark Newman in 2002. After studying one particular community detection algorithm, the so called 'Louvain algorithm', we comment on controversies arising with some of their more ambiguous applications. We argue that 'community' can act as a real abstraction with the power to reshape social relations such as producing echo chambers in social networking sites. To rework the epistemological terms of community detection, we draw on debates and propositions in the literature of network science to imagine a 'critical heuristics' that embraces partiality, epistemic humbleness, reflexivity and artificiality.
]]></description>
<dc:subject>community-detection network-theory rather-interesting define-your-terms cultural-dynamics clustering</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:70b93a24603d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:community-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cultural-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2202.09179">
    <title>[2202.09179] Incorporating Texture Information into Dimensionality Reduction for High-Dimensional Images</title>
    <dc:date>2023-02-09T12:39:53+00:00</dc:date>
    <link>https://arxiv.org/abs/2202.09179</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[High-dimensional imaging is becoming increasingly relevant in many fields from astronomy and cultural heritage to systems biology. Visual exploration of such high-dimensional data is commonly facilitated by dimensionality reduction. However, common dimensionality reduction methods do not include spatial information present in images, such as local texture features, into the construction of low-dimensional embeddings. Consequently, exploration of such data is typically split into a step focusing on the attribute space followed by a step focusing on spatial information, or vice versa. In this paper, we present a method for incorporating spatial neighborhood information into distance-based dimensionality reduction methods, such as t-Distributed Stochastic Neighbor Embedding (t-SNE). We achieve this by modifying the distance measure between high-dimensional attribute vectors associated with each pixel such that it takes the pixel's spatial neighborhood into account. Based on a classification of different methods for comparing image patches, we explore a number of different approaches. We compare these approaches from a theoretical and experimental point of view. Finally, we illustrate the value of the proposed methods by qualitative and quantitative evaluation on synthetic data and two real-world use cases.
]]></description>
<dc:subject>image-processing representation rather-interesting patterns machine-learning clustering to-write-about to-visualize consider:nonlocality</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8c6ec7deec3b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:patterns"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-visualize"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:nonlocality"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://aclanthology.org/2022.findings-acl.81/">
    <title>Learning and Evaluating Character Representations in Novels - ACL Anthology</title>
    <dc:date>2022-05-28T11:51:22+00:00</dc:date>
    <link>https://aclanthology.org/2022.findings-acl.81/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We address the problem of learning fixed-length vector representations of characters in novels. Recent advances in word embeddings have proven successful in learning entity representations from short texts, but fall short on longer documents because they do not capture full book-level information. To overcome the weakness of such text-based embeddings, we propose two novel methods for representing characters: (i) graph neural network-based embeddings from a full corpus-based character network; and (ii) low-dimensional embeddings constructed from the occurrence pattern of characters in each novel. We test the quality of these character embeddings using a new benchmark suite to evaluate character representations, encompassing 12 different tasks. We show that our representation techniques combined with text-based embeddings lead to the best character representations, outperforming text-based embeddings in four tasks. Our dataset and evaluation script will be made publicly available to stimulate additional work in this area.
]]></description>
<dc:subject>digital-humanities narrative-study natural-language-processing clustering machine-learning rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f337d5d49cf4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:narrative-study"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1711.08995">
    <title>[1711.08995] Unsupervised Domain Adaptation with Similarity Learning</title>
    <dc:date>2022-02-17T11:27:37+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.08995</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to domain adaptation consist of two steps: (i) learn features that preserve a low risk on labeled samples (source domain) and (ii) make the features from both domains to be as indistinguishable as possible, so that a classifier trained on the source can also be applied on the target domain. In general, the classifiers in step (i) consist of fully-connected layers applied directly on the indistinguishable features learned in (ii). In this paper, we propose a different way to do the classification, using similarity learning. The proposed method learns a pairwise similarity function in which classification can be performed by computing similarity between prototype representations of each category. The domain-invariant features and the categorical prototype representations are learned jointly and in an end-to-end fashion. At inference time, images from the target domain are compared to the prototypes and the label associated with the one that best matches the image is outputed. The approach is simple, scalable and effective. We show that our model achieves state-of-the-art performance in different unsupervised domain adaptation scenarios.
]]></description>
<dc:subject>performance-space-analysis neural-networks image-processing clustering</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2631df62f5fe/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-space-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1808.05689">
    <title>[1808.05689] SimGNN: A Neural Network Approach to Fast Graph Similarity Computation</title>
    <dc:date>2022-02-13T12:34:52+00:00</dc:date>
    <link>https://arxiv.org/abs/1808.05689</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Graph similarity search is among the most important graph-based applications, e.g. finding the chemical compounds that are most similar to a query compound. Graph similarity computation, such as Graph Edit Distance (GED) and Maximum Common Subgraph (MCS), is the core operation of graph similarity search and many other applications, but very costly to compute in practice. Inspired by the recent success of neural network approaches to several graph applications, such as node or graph classification, we propose a novel neural network based approach to address this classic yet challenging graph problem, aiming to alleviate the computational burden while preserving a good performance. 
The proposed approach, called SimGNN, combines two strategies. First, we design a learnable embedding function that maps every graph into a vector, which provides a global summary of a graph. A novel attention mechanism is proposed to emphasize the important nodes with respect to a specific similarity metric. Second, we design a pairwise node comparison method to supplement the graph-level embeddings with fine-grained node-level information. Our model achieves better generalization on unseen graphs, and in the worst case runs in quadratic time with respect to the number of nodes in two graphs. Taking GED computation as an example, experimental results on three real graph datasets demonstrate the effectiveness and efficiency of our approach. Specifically, our model achieves smaller error rate and great time reduction compared against a series of baselines, including several approximation algorithms on GED computation, and many existing graph neural network based models. To the best of our knowledge, we are among the first to adopt neural networks to explicitly model the similarity between two graphs, and provide a new direction for future research on graph similarity computation and graph similarity search.
]]></description>
<dc:subject>graph-theory distance metrics rather-interesting neural-networks classification clustering to-understand to-write-about consider:code-metrics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:30ad3e377134/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:code-metrics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2001.08372">
    <title>[2001.08372] ProjectionPathExplorer: Exploring Visual Patterns in Projected Decision-Making Paths</title>
    <dc:date>2022-02-12T13:48:16+00:00</dc:date>
    <link>https://arxiv.org/abs/2001.08372</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In problem-solving, a path towards solutions can be viewed as a sequence of decisions. The decisions, made by humans or computers, describe a trajectory through a high-dimensional representation space of the problem. By means of dimensionality reduction, these trajectories can be visualized in lower-dimensional space. Such embedded trajectories have previously been applied to a wide variety of data, but analysis has focused almost exclusively on the self-similarity of single trajectories. In contrast, we describe patterns emerging from drawing many trajectories---for different initial conditions, end states, and solution strategies---in the same embedding space. We argue that general statements about the problem-solving tasks and solving strategies can be made by interpreting these patterns. We explore and characterize such patterns in trajectories resulting from human and machine-made decisions in a variety of application domains: logic puzzles (Rubik's cube), strategy games (chess), and optimization problems (neural network training). We also discuss the importance of suitably chosen representation spaces and similarity metrics for the embedding.
]]></description>
<dc:subject>visualization algorithms problem-solving feature-construction rather-good planning clustering to-write-about to-visualize consider:parallel-processes consider:nonterminating-processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4d55d1bcfa39/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:problem-solving"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-good"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-visualize"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:parallel-processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:nonterminating-processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2103.06040">
    <title>[2103.06040] Subtrajectory Clustering: Finding Set Covers for Set Systems of Subcurves</title>
    <dc:date>2022-02-03T16:58:49+00:00</dc:date>
    <link>https://arxiv.org/abs/2103.06040</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We study subtrajectory clustering under the Fréchet distance. Given one or more trajectories, the task is to split the trajectories into several parts, such that the parts have a good clustering structure. We approach this problem via a new set cover formulation, which we think provides a natural formalization of the problem as it is studied in many applications. Given a polygonal curve P with n vertices in fixed dimension, integers k, ℓ≥1, and a real value Δ>0, the goal is to find k center curves of complexity at most ℓ such that every point on P is covered by a subtrajectory that has small Fréchet distance to one of the k center curves (≤Δ). In many application scenarios, one is interested in finding clusters of small complexity, which is controlled by the parameter ℓ. Our main result is a bicriterial approximation algorithm: if there exists a solution for given parameters k, ℓ, and Δ, then our algorithm finds a set of k′ center curves of complexity at most ℓ with covering radius Δ′ with k′∈O(kℓ2log(kℓ)), and Δ′≤19Δ. Moreover, within these approximation bounds, we can minimize k while keeping the other parameters fixed. If ℓ is a constant independent of n, then, the approximation factor for the number of clusters k is O(logk) and the approximation factor for the radius Δ is constant. In this case, the algorithm has expected running time in Õ(km2+mn) and uses space in O(n+m), where m=⌈LΔ⌉ and L is the total arclength of the curve P.
]]></description>
<dc:subject>computational-geometry clustering rather-interesting feature-construction trajectories agents to-write-about to-reimplement</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3c1cf7ac8479/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:trajectories"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:agents"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-reimplement"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.03972">
    <title>[1810.03972] Machine learning clustering technique applied to powder X-ray diffraction patterns to distinguish alloy substitutions</title>
    <dc:date>2021-07-21T21:40:07+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.03972</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We applied the clustering technique using DTW (dynamic time wrapping) analysis to XRD (X-ray diffraction) spectrum patterns in order to identify the microscopic structures of substituents introduced in the main phase of magnetic alloys. The clustering is found to perform well to identify the concentrations of the substituents with successful rates (around 90%). The sufficient performance is attributed to the nature of DTW processing to filter out irrelevant informations such as the peak intensities (due to the incontrollability of diffraction conditions in polycrystalline samples) and the uniform shift of peak positions (due to the thermal expansions of lattices).
]]></description>
<dc:subject>crystallography machine-learning clustering rather-interesting spectra to-write-about synthetic-data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6dcee0ddaeab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:crystallography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:spectra"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:synthetic-data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://astrobiology.com/2021/04/inferring-exoplanet-disequilibria-with-multivariate-information-in-atmospheric-reaction-networks.html">
    <title>Inferring Exoplanet Disequilibria with Multivariate Information in Atmospheric Reaction Networks - Astrobiology</title>
    <dc:date>2021-05-18T22:08:56+00:00</dc:date>
    <link>http://astrobiology.com/2021/04/inferring-exoplanet-disequilibria-with-multivariate-information-in-atmospheric-reaction-networks.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Inferring the properties of exoplanets from their atmospheres, while confronting low resolution and low signal-to-noise in the context of the quantities we want to derive, poses rigorous demands upon the data collected from observation.

]]></description>
<dc:subject>astrobiology rather-interesting data-analysis spectroscopy machine-learning clustering nonlinear-dynamics origin-of-life</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a6299daa7b34/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:astrobiology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:spectroscopy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:origin-of-life"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1807.06414">
    <title>[1807.06414] Combining a Context Aware Neural Network with a Denoising Autoencoder for Measuring String Similarities</title>
    <dc:date>2020-02-16T13:08:12+00:00</dc:date>
    <link>https://arxiv.org/abs/1807.06414</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Measuring similarities between strings is central for many established and fast growing research areas including information retrieval, biology, and natural language processing. The traditional approach for string similarity measurements is to define a metric over a word space that quantifies and sums up the differences between characters in two strings. The state-of-the-art in the area has, surprisingly, not evolved much during the last few decades. The majority of the metrics are based on a simple comparison between character and character distributions without consideration for the context of the words. This paper proposes a string metric that encompasses similarities between strings based on (1) the character similarities between the words including. Non-Standard and standard spellings of the same words, and (2) the context of the words. Our proposal is a neural network composed of a denoising autoencoder and what we call a context encoder specifically designed to find similarities between the words based on their context. The experimental results show that the resulting metrics succeeds in 85.4\% of the cases in finding the correct version of a non-standard spelling among the closest words, compared to 63.2\% with the established Normalised-Levenshtein distance. Besides, we show that words used in similar context are with our approach calculated to be similar than words with different contexts, which is a desirable property missing in established string metrics.
]]></description>
<dc:subject>feature-construction machine-learning clustering natural-language-processing rather-interesting to-simulate to-write-about consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e79ce779e77d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://proceedings.mlr.press/v54/hong17a.html">
    <title>High-dimensional Time Series Clustering via Cross-Predictability</title>
    <dc:date>2020-02-16T12:35:48+00:00</dc:date>
    <link>http://proceedings.mlr.press/v54/hong17a.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The key to time series clustering is how to characterize the similarity between any two time series. In this paper, we explore a new similarity metric called “cross-predictability”: the degree to which a future value in each time series is predicted by past values of the others. However, it is challenging to estimate such cross-predictability among time series in the high-dimensional regime, where the number of time series is much larger than the length of each time series. We address this challenge with a sparsity assumption: only time series in the same cluster have significant cross-predictability with each other. We demonstrate that this approach is computationally attractive, and provide a theoretical proof that the proposed algorithm will identify the correct clustering structure with high probability under certain conditions. To the best of our knowledge, this is the first practical high-dimensional time series clustering algorithm with a provable guarantee. We evaluate with experiments on both synthetic data and real-world data, and results indicate that our method can achieve more than 80% clustering accuracy on real-world data, which is 20% higher than the state-of-art baselines.
]]></description>
<dc:subject>performance-networks clustering time-series yeah-I-probably-shoulda-published-in-1999 machine-learning feature-construction ah-well</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f681052a7c11/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:yeah-I-probably-shoulda-published-in-1999"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ah-well"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1602.04181">
    <title>[1602.04181] Spectral Alignment of Graphs</title>
    <dc:date>2019-09-28T10:51:59+00:00</dc:date>
    <link>https://arxiv.org/abs/1602.04181</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Graph alignment refers to the problem of finding a bijective mapping across vertices of two graphs such that, if two nodes are connected in the first graph, their images are connected in the second graph. This problem arises in many fields such as computational biology, social sciences, and computer vision and is often cast as a quadratic assignment problem (QAP). Most standard graph alignment methods consider an optimization that maximizes the number of matches between the two graphs, ignoring the effect of mismatches. We propose a generalized graph alignment formulation that considers both matches and mismatches in a standard QAP formulation. This modification can have a major impact in aligning graphs with different sizes and heterogenous edge densities. Moreover, we propose two methods for solving the generalized graph alignment problem based on spectral decomposition of matrices. We compare the performance of proposed methods with some existing graph alignment algorithms including Natalie2, GHOST, IsoRank, NetAlign, Klau's approach as well as a semidefinite programming-based method over various synthetic and real graph models. Our proposed method based on simultaneous alignment of multiple eigenvectors leads to consistently good performance in different graph models. In particular, in the alignment of regular graph structures which is one of the most difficult graph alignment cases, our proposed method significantly outperforms other methods.
]]></description>
<dc:subject>graph-theory similarity-measures clustering distance numerical-methods algorithms performance-measure rather-interesting consider:looking-to-see consider:robustness to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d47a66c1988f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:similarity-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:robustness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1808.05740">
    <title>[1808.05740] Extremality, Stationarity and Generalized Separation of Collections of Sets</title>
    <dc:date>2019-09-25T10:31:11+00:00</dc:date>
    <link>https://arxiv.org/abs/1808.05740</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The core arguments used in various proofs of the extremal principle and its extensions as well as in primal and dual characterizations of approximate stationarity and transversality of collections of sets are exposed, analyzed and refined, leading to a unifying theory, encompassing all existing approaches to obtaining 'extremal' statements. For that, we examine and clarify quantitative relationships between the parameters involved in the respective definitions and statements. Some new characterizations of extremality properties are obtained.
]]></description>
<dc:subject>statistics clustering extreme-values to-understand discrimination algorithms rather-odd rather-general-sounding optimization probability-theory consider:weird-GP-stuff</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d7f86b2621f8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:extreme-values"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrimination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-odd"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-general-sounding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:weird-GP-stuff"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1510.00850">
    <title>[1510.00850] Maximum Likelihood Latent Space Embedding of Logistic Random Dot Product Graphs</title>
    <dc:date>2019-09-25T10:25:10+00:00</dc:date>
    <link>https://arxiv.org/abs/1510.00850</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A latent space model for a family of random graphs assigns real-valued vectors to nodes of the graph such that edge probabilities are determined by latent positions. Latent space models provide a natural statistical framework for graph visualizing and clustering. A latent space model of particular interest is the Random Dot Product Graph (RDPG), which can be fit using an efficient spectral method; however, this method is based on a heuristic that can fail, even in simple cases. Here, we consider a closely related latent space model, the Logistic RDPG, which uses a logistic link function to map from latent positions to edge likelihoods. Over this model, we show that asymptotically exact maximum likelihood inference of latent position vectors can be achieved using an efficient spectral method. Our method involves computing top eigenvectors of a normalized adjacency matrix and scaling eigenvectors using a regression step. The novel regression scaling step is an essential part of the proposed method. In simulations, we show that our proposed method is more accurate and more robust than common practices. We also show the effectiveness of our approach over standard real networks of the karate club and political blogs.
]]></description>
<dc:subject>clustering feature-construction rather-interesting spectra graph-theory metrics to-understand to-write-about consider:program-trace-comparisons</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:830601bf7639/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:spectra"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:program-trace-comparisons"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.08237">
    <title>[1810.08237] Large-scale Hierarchical Alignment for Data-driven Text Rewriting</title>
    <dc:date>2019-08-06T10:14:16+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.08237</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news articles and scientific papers. Our approach does not require a seed parallel corpus, but instead relies solely on hierarchical search over pre-trained embeddings of documents and sentences. We demonstrate the effectiveness of our method through automatic and extrinsic evaluation on text simplification from the normal to the Simple Wikipedia. We show that pseudo-parallel sentences extracted with our method not only supplement existing parallel data, but can even lead to competitive performance on their own.
]]></description>
<dc:subject>natural-language-processing text-mining translation rather-interesting algorithms representation machine-learning clustering unsupervised-learning to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ef18c7dc07ba/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:translation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unsupervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.01910">
    <title>[1811.01910] Evolutionary Data Measures: Understanding the Difficulty of Text Classification Tasks</title>
    <dc:date>2019-07-25T11:03:05+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.01910</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Classification tasks are usually analysed and improved through new model architectures or hyperparameter optimisation but the underlying properties of datasets are discovered on an ad-hoc basis as errors occur. However, understanding the properties of the data is crucial in perfecting models. In this paper we analyse exactly which characteristics of a dataset best determine how difficult that dataset is for the task of text classification. We then propose an intuitive measure of difficulty for text classification datasets which is simple and fast to calculate. We show that this measure generalises to unseen data by comparing it to state-of-the-art datasets and results. This measure can be used to analyse the precise source of errors in a dataset and allows fast estimation of how difficult a dataset is to learn. We searched for this measure by training 12 classical and neural network based models on 78 real-world datasets, then use a genetic algorithm to discover the best measure of difficulty. Our difficulty-calculating code ( this https URL ) and datasets ( this http URL ) are publicly available.
]]></description>
<dc:subject>machine-learning performance-measure performance-space-analysis clustering adversarial-testing to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:db970d1f461e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-space-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:adversarial-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.04816">
    <title>[1810.04816] Clustering via Hypergraph Modularity</title>
    <dc:date>2019-04-19T21:00:26+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.04816</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Despite the fact that many important problems (including clustering) can be described using hypergraphs, theoretical foundations as well as practical algorithms using hypergraphs are not well developed yet. In this paper, we propose a hypergraph modularity function that generalizes its well established and widely used graph counterpart measure of how clustered a network is. In order to define it properly, we generalize the Chung-Lu model for graphs to hypergraphs. We then provide the theoretical foundations to search for an optimal solution with respect to our hypergraph modularity function. Two simple heuristic algorithms are described and applied to a few small illustrative examples. We show that using a strict version of our proposed modularity function often leads to a solution where a smaller number of hyperedges get cut as compared to optimizing modularity of 2-section graph of a hypergraph.
]]></description>
<dc:subject>clustering hypergraphs representation algorithms combinatorics rather-interesting feature-selection</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:01c9bc4566c0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hypergraphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:combinatorics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-selection"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.06912">
    <title>[1811.06912] Exploring Student Check-In Behavior for Improved Point-of-Interest Prediction</title>
    <dc:date>2019-04-10T10:28:38+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.06912</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[With the availability of vast amounts of user visitation history on location-based social networks (LBSN), the problem of Point-of-Interest (POI) prediction has been extensively studied. However, much of the research has been conducted solely on voluntary checkin datasets collected from social apps such as Foursquare or Yelp. While these data contain rich information about recreational activities (e.g., restaurants, nightlife, and entertainment), information about more prosaic aspects of people's lives is sparse. This not only limits our understanding of users' daily routines, but more importantly the modeling assumptions developed based on characteristics of recreation-based data may not be suitable for richer check-in data. In this work, we present an analysis of education "check-in" data using WiFi access logs collected at Purdue University. We propose a heterogeneous graph-based method to encode the correlations between users, POIs, and activities, and then jointly learn embeddings for the vertices. We evaluate our method compared to previous state-of-the-art POI prediction methods, and show that the assumptions made by previous methods significantly degrade performance on our data with dense(r) activity signals. We also show how our learned embeddings could be used to identify similar students (e.g., for friend suggestions).
]]></description>
<dc:subject>social-dynamics social-networks data-analysis rather-interesting statistics machine-learning clustering data-pageant visualization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:178a4234fb86/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-pageant"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1809.02786">
    <title>[1809.02786] Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples</title>
    <dc:date>2019-02-19T10:52:27+00:00</dc:date>
    <link>https://arxiv.org/abs/1809.02786</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Adversarial examples are perturbed inputs designed to fool machine learning models. Most recent works on adversarial examples for image classification focus on directly modifying pixels with minor perturbations. A common requirement in all these works is that the malicious perturbations should be small enough (measured by an L_p norm for some p) so that they are imperceptible to humans. However, small perturbations can be unnecessarily restrictive and limit the diversity of adversarial examples generated. Further, an L_p norm based distance metric ignores important structure patterns hidden in images that are important to human perception. Consequently, even the minor perturbation introduced in recent works often makes the adversarial examples less natural to humans. More importantly, they often do not transfer well and are therefore less effective when attacking black-box models especially for those protected by a defense mechanism. In this paper, we propose a structure-preserving transformation (SPT) for generating natural and diverse adversarial examples with extremely high transferability. The key idea of our approach is to allow perceptible deviation in adversarial examples while keeping structure patterns that are central to a human classifier. Empirical results on the MNIST and the fashion-MNIST datasets show that adversarial examples generated by our approach can easily bypass strong adversarial training. Further, they transfer well to other target models with no loss or little loss of successful attack rate.
]]></description>
<dc:subject>adversarial-tricks neural-networks image-processing clustering deep-learning rather-interesting feature-intuiting to-write-about consider:genetic-programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:731aa2f65a42/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:adversarial-tricks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-intuiting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1902.01023">
    <title>[1902.01023] Enhanced Hierarchical Music Structure Annotations via Feature Level Similarity Fusion</title>
    <dc:date>2019-02-13T11:46:16+00:00</dc:date>
    <link>https://arxiv.org/abs/1902.01023</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We describe a novel pipeline to automatically discover hierarchies of repeated sections in musical audio. The proposed method uses similarity network fusion (SNF) to combine different frame-level features into clean affinity matrices, which are then used as input to spectral clustering. While prior spectral clustering approaches to music structure analysis have pre-processed affinity matrices with heuristics specifically designed for this task, we show that the SNF approach directly yields segmentations which agree better with human annotators, as measured by the ``L-measure'' metric for hierarchical annotations. Furthermore, the SNF approach immediately supports arbitrarily many input features, allowing us to simultaneously discover structure encoded in timbral, harmonic, and rhythmic representations without any changes to the base algorithm.
]]></description>
<dc:subject>classification clustering music feature-construction rather-interesting indexing to-write-about performance-measure</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:eebcaf05ed47/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:music"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:indexing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5411762/">
    <title>Genome graphs and the evolution of genome inference</title>
    <dc:date>2019-02-13T10:43:47+00:00</dc:date>
    <link>https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5411762/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The human reference genome is part of the foundation of modern human biology and a monumental scientific achievement. However, because it excludes a great deal of common human variation, it introduces a pervasive reference bias into the field of human genomics. To reduce this bias, it makes sense to draw on representative collections of human genomes, brought together into reference cohorts. There are a number of techniques to represent and organize data gleaned from these cohorts, many using ideas implicitly or explicitly borrowed from graph-based models. Here, we survey various projects underway to build and apply these graph-based structures—which we collectively refer to as genome graphs—and discuss the improvements in read mapping, variant calling, and haplotype determination that genome graphs are expected to produce.

]]></description>
<dc:subject>via:arthegall bioinformatics clustering visualization data-analysis rather-interesting consider:nonbiological-genomes review</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8e2e925902f0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:nonbiological-genomes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:review"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1704.00454">
    <title>[1704.00454] Clustering in Hilbert simplex geometry</title>
    <dc:date>2019-01-08T11:22:48+00:00</dc:date>
    <link>https://arxiv.org/abs/1704.00454</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Clustering categorical distributions in the probability simplex is a fundamental task met in many applications dealing with normalized histograms. Traditionally, the differential-geometric structures of the probability simplex have been used either by (i) setting the Riemannian metric tensor to the Fisher information matrix of the categorical distributions, or (ii) defining the dualistic information-geometric structure induced by a smooth dissimilarity measure, the Kullback-Leibler divergence. In this work, we introduce for this clustering task a novel computationally-friendly framework for modeling the probability simplex termed {\em Hilbert simplex geometry}. In the Hilbert simplex geometry, the distance function is described by a polytope. We discuss the pros and cons of those different statistical modelings, and benchmark experimentally these geometries for center-based k-means and k-center clusterings. We show that Hilbert metric in the probability simplex satisfies the property of information monotonicity. Furthermore, since a canonical Hilbert metric distance can be defined on any bounded convex subset of the Euclidean space, we also consider Hilbert's projective geometry of the elliptope of correlation matrices and study its clustering performances.]]></description>
<dc:subject>clustering representation categorical-variables rather-interesting machine-learning to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c25cd4ce56f4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:categorical-variables"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1512.04349">
    <title>[1512.04349] Clustering time series under the Fr'echet distance</title>
    <dc:date>2018-11-29T01:30:16+00:00</dc:date>
    <link>https://arxiv.org/abs/1512.04349</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[e Fréchet distance is a popular distance measure for curves. We study the problem of clustering time series under the Fréchet distance. In particular, we give (1+ε)-approximation algorithms for variations of the following problem with parameters k and ℓ. Given n univariate time series P, each of complexity at most m, we find k time series, not necessarily from P, which we call \emph{cluster centers} and which each have complexity at most ℓ, such that (a) the maximum distance of an element of P to its nearest cluster center or (b) the sum of these distances is minimized. Our algorithms have running time near-linear in the input size for constant ε, k and ℓ. To the best of our knowledge, our algorithms are the first clustering algorithms for the Fréchet distance which achieve an approximation factor of (1+ε) or better. 
Keywords: time series, longitudinal data, functional data, clustering, Fréchet distance, dynamic time warping, approximation algorithms.]]></description>
<dc:subject>computational-geometry algorithms metrics clustering to-understand time-series</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:83889eedc755/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.pnas.org/content/early/2018/08/28/1810575115">
    <title>Evolution of metazoan morphological disparity | PNAS</title>
    <dc:date>2018-10-20T12:28:55+00:00</dc:date>
    <link>http://www.pnas.org/content/early/2018/08/28/1810575115</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We attempt to quantify animal “bodyplans” and their variation within Metazoa. Our results challenge the view that maximum variation was achieved early in animal evolutionary history by nonuniformitarian mechanisms. Rather, they are compatible with the view that the capacity for fundamental innovation is not limited to the early evolutionary history of clades. We perform quantitative tests of the principal hypotheses of the molecular mechanisms underpinning the establishment of animal bodyplans and corroborate the hypothesis that animal evolution has been permitted or driven by gene regulatory evolution.

]]></description>
<dc:subject>developmental-biology biology rather-interesting clustering looking-to-see to-write-about consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d89b1da98a11/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:developmental-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1804.00222">
    <title>[1804.00222] Learning Unsupervised Learning Rules</title>
    <dc:date>2018-04-06T13:52:02+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.00222</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this goal is approached by minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations useful for subsequent tasks will arise as a side effect. In this work, we propose instead to directly target a later desired task by meta-learning an unsupervised learning rule, which leads to representations useful for that task. Here, our desired task (meta-objective) is the performance of the representation on semi-supervised classification, and we meta-learn an algorithm -- an unsupervised weight update rule -- that produces representations that perform well under this meta-objective. Additionally, we constrain our unsupervised update rule to a be a biologically-motivated, neuron-local function, which enables it to generalize to novel neural network architectures. We show that the meta-learned update rule produces useful features and sometimes outperforms existing unsupervised learning techniques. We show that the meta-learned unsupervised update rule generalizes to train networks with different widths, depths, and nonlinearities. It also generalizes to train on data with randomly permuted input dimensions and even generalizes from image datasets to a text task.
]]></description>
<dc:subject>machine-learning unsupervised-learning rather-interesting feature-extraction clustering algorithms to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fed2632c470e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unsupervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.04594">
    <title>[1709.04594] Revisiting Spectral Graph Clustering with Generative Community Models</title>
    <dc:date>2018-03-19T09:40:47+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.04594</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The methodology of community detection can be divided into two principles: imposing a network model on a given graph, or optimizing a designed objective function. The former provides guarantees on theoretical detectability but falls short when the graph is inconsistent with the underlying model. The latter is model-free but fails to provide quality assurance for the detected communities. In this paper, we propose a novel unified framework to combine the advantages of these two principles. The presented method, SGC-GEN, not only considers the detection error caused by the corresponding model mismatch to a given graph, but also yields a theoretical guarantee on community detectability by analyzing Spectral Graph Clustering (SGC) under GENerative community models (GCMs). SGC-GEN incorporates the predictability on correct community detection with a measure of community fitness to GCMs. It resembles the formulation of supervised learning problems by enabling various community detection loss functions and model mismatch metrics. We further establish a theoretical condition for correct community detection using the normalized graph Laplacian matrix under a GCM, which provides a novel data-driven loss function for SGC-GEN. In addition, we present an effective algorithm to implement SGC-GEN, and show that the computational complexity of SGC-GEN is comparable to the baseline methods. Our experiments on 18 real-world datasets demonstrate that SGC-GEN possesses superior and robust performance compared to 6 baseline methods under 7 representative clustering metrics.
]]></description>
<dc:subject>community-detection network-theory algorithms looking-to-see clustering to-write-about the-pragmatics-of-the-thing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a1f44d95f317/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:community-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:the-pragmatics-of-the-thing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1802.03426">
    <title>[1802.03426] UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction</title>
    <dc:date>2018-03-10T13:30:32+00:00</dc:date>
    <link>https://arxiv.org/abs/1802.03426</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[UMAP (Uniform Manifold Approximation and Projection) is a novel manifold learning technique for dimension reduction. UMAP is constructed from a theoretical framework based in Riemannian geometry and algebraic topology. The result is a practical scalable algorithm that applies to real world data. The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance. Furthermore, UMAP as described has no computational restrictions on embedding dimension, making it viable as a general purpose dimension reduction technique for machine learning.]]></description>
<dc:subject>clustering visualization machine-learning algorithms performance-measure rather-interesting to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:955acb780143/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1404.1008">
    <title>[1404.1008] Spectral concentration and greedy k-clustering</title>
    <dc:date>2017-11-09T18:13:35+00:00</dc:date>
    <link>https://arxiv.org/abs/1404.1008</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A popular graph clustering method is to consider the embedding of an input graph into R^k induced by the first k eigenvectors of its Laplacian, and to partition the graph via geometric manipulations on the resulting metric space. Despite the practical success of this methodology, there is limited understanding of several heuristics that follow this framework. We provide theoretical justification for one such natural and computationally efficient variant. 
Our result can be summarized as follows. A partition of a graph is called strong if each cluster has small external conductance, and large internal conductance. We present a simple greedy spectral clustering algorithm which returns a partition that is provably close to a suitably strong partition, provided that such a partition exists. A recent result shows that strong partitions exist for graphs with a sufficiently large spectral gap between the k-th and (k+1)-th eigenvalues. Taking this together with our main theorem gives a spectral algorithm which finds a partition close to a strong one for graphs with large enough spectral gap. We also show how this simple greedy algorithm can be implemented in near-linear time for any fixed k and error guarantee. Finally, we evaluate our algorithm on some real-world and synthetic inputs.]]></description>
<dc:subject>clustering graph-theory algorithms rather-interesting heuristics performance-measure to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:943a8b58d439/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1604.03159">
    <title>[1604.03159] Phase Transitions and a Model Order Selection Criterion for Spectral Graph Clustering</title>
    <dc:date>2017-10-12T11:16:04+00:00</dc:date>
    <link>https://arxiv.org/abs/1604.03159</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[One of the longstanding open problems in spectral graph clustering (SGC) is the so-called model order selection problem: automated selection of the correct number of clusters. This is equivalent to the problem of finding the number of connected components or communities in an undirected graph. We propose automated model order selection (AMOS), a solution to the SGC model selection problem under a random interconnection model (RIM) using a novel selection criterion that is based on an asymptotic phase transition analysis. AMOS can more generally be applied to discovering hidden block diagonal structure in symmetric non-negative matrices. Numerical experiments on simulated graphs validate the phase transition analysis, and real-world network data is used to validate the performance of the proposed model selection procedure.]]></description>
<dc:subject>network-theory clustering community-detection algorithms performance-measure rather-interesting consider:looking-to-see consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9b8d5a0eb0dc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:community-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.07797">
    <title>[1709.07797] Intrinsic Metrics: Nearest Neighbor and Edge Squared Distances</title>
    <dc:date>2017-09-26T14:33:44+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.07797</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Some researchers have proposed using non-Euclidean metrics for clustering data points. Generally, the metric should recognize that two points in the same cluster are close, even if their Euclidean distance is far. Multiple proposals have been suggested, including the Edge-Squared Metric (a specific example of a graph geodesic) and the Nearest Neighbor Metric. 
In this paper, we prove that the edge-squared and nearest-neighbor metrics are in fact equivalent. Previous best work showed that the edge-squared metric was a 3-approximation of the Nearest Neighbor metric. This paper represents one of the first proofs of equating a continuous metric with a discrete metric, using non-trivial discrete methods. Our proof uses the Kirszbraun theorem (also known as the Lipschitz Extension Theorem and Brehm's Extension Theorem), a notable theorem in functional analysis and computational geometry. 
The results of our paper, combined with the results of Hwang, Damelin, and Hero, tell us that the Nearest Neighbor distance on i.i.d samples of a density is a reasonable constant approximation of a natural density-based distance function.]]></description>
<dc:subject>clustering metrics statistics amusing one-of-these-things-is-just-like-the-other computational-geometry</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:38f2196a8106/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:amusing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:one-of-these-things-is-just-like-the-other"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.07321">
    <title>[1705.07321] Accelerated Hierarchical Density Clustering</title>
    <dc:date>2017-09-26T14:16:15+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.07321</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We present an accelerated algorithm for hierarchical density based clustering. Our new algorithm improves upon HDBSCAN*, which itself provided a significant qualitative improvement over the popular DBSCAN algorithm. The accelerated HDBSCAN* algorithm provides comparable performance to DBSCAN, while supporting variable density clusters, and eliminating the need for the difficult to tune distance scale parameter. This makes accelerated HDBSCAN* the default choice for density based clustering. 
]]></description>
<dc:subject>clustering algorithms statistics computational-complexity nudge-targets consider:looking-to-see consider:lexicase</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6163b46f142d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:lexicase"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1507.03067">
    <title>[1507.03067] Micro-Clustering: Finding Small Clusters in Large Diversity</title>
    <dc:date>2017-04-29T11:32:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1507.03067</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We address the problem of un-supervised soft-clustering called micro-clustering. The aim of the problem is to enumerate all groups composed of records strongly related to each other, while standard clustering methods separate records at sparse parts. The problem formulation of micro-clustering is non-trivial. Clique mining in a similarity graph is a typical approach, but it results in a huge number of cliques that are of many similar cliques. We propose a new concept data polishing. The cause of huge solutions can be considered that the groups are not clear in the data, that is, the boundaries of the groups are not clear, because of noise, uncertainty, lie, lack, etc. Data polishing clarifies the groups by perturbating the data. Specifically, dense subgraphs that would correspond to clusters are replaced by cliques. The clusters are clarified as maximal cliques, thus the number of maximal cliques will be drastically reduced. We also propose an efficient algorithm applicable even for large scale data. Computational experiments showed the efficiency of our algorithm, i.e., the number of solutions is small, (e.g., 1,000), the members of each group are deeply related, and the computation time is short.
]]></description>
<dc:subject>graph-theory network-theory clustering rather-interesting define-your-terms to-understand out-of-the-box philosophy-of-engineering feature-construction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:39db3d227d2e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:out-of-the-box"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1703.04823">
    <title>[1703.04823] Classification in biological networks with hypergraphlet kernels</title>
    <dc:date>2017-04-17T10:30:55+00:00</dc:date>
    <link>https://arxiv.org/abs/1703.04823</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Biological and cellular systems are often modeled as graphs in which vertices represent objects of interest (genes, proteins, drugs) and edges represent relational ties among these objects (binds-to, interacts-with, regulates). This approach has been highly successful owing to the theory, methodology and software that support analysis and learning on graphs. Graphs, however, often suffer from information loss when modeling physical systems due to their inability to accurately represent multiobject relationships. Hypergraphs, a generalization of graphs, provide a framework to mitigate information loss and unify disparate graph-based methodologies. In this paper, we present a hypergraph-based approach for modeling physical systems and formulate vertex classification, edge classification and link prediction problems on (hyper)graphs as instances of vertex classification on (extended, dual) hypergraphs in a semi-supervised setting. We introduce a novel kernel method on vertex- and edge-labeled (colored) hypergraphs for analysis and learning. The method is based on exact and inexact (via hypergraph edit distances) enumeration of small simple hypergraphs, referred to as hypergraphlets, rooted at a vertex of interest. We extensively evaluate this method and show its potential use in a positive-unlabeled setting to estimate the number of missing and false positive links in protein-protein interaction networks.
]]></description>
<dc:subject>machine-learning representation rather-interesting hypergraphs to-write-about nudge-targets consider:representation consider:looking-to-see bioinformatics clustering metrics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d6f591f5708d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hypergraphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1704.00794">
    <title>[1704.00794] Time Series Cluster Kernel for Learning Similarities between Multivariate Time Series with Missing Data</title>
    <dc:date>2017-04-05T11:21:28+00:00</dc:date>
    <link>https://arxiv.org/abs/1704.00794</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Similarity-based approaches represent a promising direction for time series analysis. However, many such methods rely on parameter tuning and have shortcomings if the time series are multivariate (MTS) and contain missing data. In this paper, we address these challenges within the powerful context of kernel methods by proposing the robust \emph{time series cluster kernel} (TCK). The approach taken is to leverage the missing data handling properties of Gaussian mixture models (GMM) augmented with informative prior distributions. An ensemble learning approach is exploited to ensure robustness to parameters by combining the clustering results of many GMM to form the final kernel. 
We evaluate the TCK on synthetic and real data and compare to other state-of-the-art techniques. The experimental results demonstrate that the TCK is robust to parameter choices, provides competitive results for MTS without missing data and outstanding results for missing data.]]></description>
<dc:subject>time-series clustering feature-extraction statistics algorithms nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c2e00719e4a2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1608.03544">
    <title>[1608.03544] On Context-Dependent Clustering of Bandits</title>
    <dc:date>2017-03-21T23:59:26+00:00</dc:date>
    <link>https://arxiv.org/abs/1608.03544</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We investigate a novel cluster-of-bandit algorithm CAB for collaborative recommendation tasks that implements the underlying feedback sharing mechanism by estimating the neighborhood of users in a context-dependent manner. CAB makes sharp departures from the state of the art by incorporating collaborative effects into inference as well as learning processes in a manner that seamlessly interleaving explore-exploit tradeoffs and collaborative steps. We prove regret bounds under various assumptions on the data, which exhibit a crisp dependence on the expected number of clusters over the users, a natural measure of the statistical difficulty of the learning task. Experiments on production and real-world datasets show that CAB offers significantly increased prediction performance against a representative pool of state-of-the-art methods.
]]></description>
<dc:subject>recommendations exploration exploitation machine-learning algorithms clustering rather-interesting to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ba2b001a6eb1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:recommendations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:exploration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:exploitation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1501.01822">
    <title>[1501.01822] Central Trajectories</title>
    <dc:date>2017-03-21T12:46:45+00:00</dc:date>
    <link>https://arxiv.org/abs/1501.01822</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[An important task in trajectory analysis is clustering. The results of a clustering are often summarized by a single representative trajectory and an associated size of each cluster. We study the problem of computing a suitable representative of a set of similar trajectories. To this end we define a central trajectory , which consists of pieces of the input trajectories, switches from one entity to another only if they are within a small distance of each other, and such that at any time t, the point (t) is as central as possible. We measure centrality in terms of the radius of the smallest disk centered at (t) enclosing all entities at time t, and discuss how the techniques can be adapted to other measures of centrality. We first study the problem in ℝ1, where we show that an optimal central trajectory  representing n trajectories, each consisting of τ edges, has complexity Θ(τn2) and can be computed in O(τn2logn) time. We then consider trajectories in ℝd with d≥2, and show that the complexity of  is at most O(τn5/2) and can be computed in O(τn3) time.
]]></description>
<dc:subject>clustering computational-geometry algorithms rather-interesting nudge-targets consider:looking-to-see optimization computational-complexity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:de47772ff7e9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1603.06252">
    <title>[1603.06252] Grouping Time-varying Data for Interactive Exploration</title>
    <dc:date>2017-03-21T12:35:43+00:00</dc:date>
    <link>https://arxiv.org/abs/1603.06252</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We present algorithms and data structures that support the interactive analysis of the grouping structure of one-, two-, or higher-dimensional time-varying data while varying all defining parameters. Grouping structures characterise important patterns in the temporal evaluation of sets of time-varying data. We follow Buchin et al. [JoCG 2015] who define groups using three parameters: group-size, group-duration, and inter-entity distance. We give upper and lower bounds on the number of maximal groups over all parameter values, and show how to compute them efficiently. Furthermore, we describe data structures that can report changes in the set of maximal groups in an output-sensitive manner. Our results hold in ℝd for fixed d.]]></description>
<dc:subject>clustering feature-construction rather-interesting to-understand consider:performance-space-analysis compare-to-Pareto-GP-features visualization approximation to-write-about algorithms computational-geometry</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:dce1b289fa86/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-space-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:compare-to-Pareto-GP-features"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1606.07312">
    <title>[1606.07312] Unsupervised preprocessing for Tactile Data</title>
    <dc:date>2017-03-11T13:23:39+00:00</dc:date>
    <link>https://arxiv.org/abs/1606.07312</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Tactile information is important for gripping, stable grasp, and in-hand manipulation, yet the complexity of tactile data prevents widespread use of such sensors. We make use of an unsupervised learning algorithm that transforms the complex tactile data into a compact, latent representation without the need to record ground truth reference data. These compact representations can either be used directly in a reinforcement learning based controller or can be used to calibrate the tactile sensor to physical quantities with only a few datapoints. We show the quality of our latent representation by predicting important features and with a simple control task.
]]></description>
<dc:subject>rather-interesting sensors robotics clustering machine-learning nudge-targets consider:looking-to-see consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c2714aa35823/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sensors"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robotics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.nature.com/nmeth/journal/v12/n3/abs/nmeth.3254.html">
    <title>Inferring biological tasks using Pareto analysis of high-dimensional data : Nature Methods : Nature Research</title>
    <dc:date>2017-02-27T14:57:21+00:00</dc:date>
    <link>http://www.nature.com/nmeth/journal/v12/n3/abs/nmeth.3254.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We present the Pareto task inference method (ParTI; http://www.weizmann.ac.il/mcb/UriAlon/download/ParTI) for inferring biological tasks from high-dimensional biological data. Data are described as a polytope, and features maximally enriched closest to the vertices (or archetypes) allow identification of the tasks the vertices represent. We demonstrate that human breast tumors and mouse tissues are well described by tetrahedrons in gene expression space, with specific tumor types and biological functions enriched at each of the vertices, suggesting four key tasks.

]]></description>
<dc:subject>archetypal-analysis clustering bioinformatics systems-biology machine-learning algorithms rather-interesting to-write-about nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:cdfd7e23fcd5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:archetypal-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.sciencedirect.com/science/article/pii/S1751157712001034">
    <title>Archetypal scientists</title>
    <dc:date>2017-02-27T01:37:18+00:00</dc:date>
    <link>http://www.sciencedirect.com/science/article/pii/S1751157712001034</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce archetypal analysis as a tool to describe and categorize scientists. This approach identifies typical characteristics of extreme (‘archetypal’) values in a multivariate data set. These positive or negative contextual attributes can be allocated to each scientist under investigation. In our application, we use a sample of seven bibliometric indicators for 29,083 economists obtained from the RePEc database and identify six archetypes. These are mainly characterized by ratios of published work and citations. We discuss applications and limitations of this approach. Finally, we assign relative shares of the identified archetypes to each economist in our sample.

]]></description>
<dc:subject>archetypal-analysis amusing data-analysis machine-learning statistics clustering to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:69a1035ab556/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:archetypal-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:amusing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://ieeexplore.ieee.org/abstract/document/5589222/">
    <title>Archetypal analysis for machine learning - IEEE Xplore Document</title>
    <dc:date>2017-02-27T01:35:11+00:00</dc:date>
    <link>http://ieeexplore.ieee.org/abstract/document/5589222/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Archetypal analysis (AA) proposed by Cutler and Breiman in [1] estimates the principal convex hull of a data set. As such AA favors features that constitute representative 'corners' of the data, i.e. distinct aspects or archetypes. We will show that AA enjoys the interpretability of clustering - without being limited to hard assignment and the uniqueness of SVD - without being limited to orthogonal representations. In order to do large scale AA, we derive an efficient algorithm based on projected gradient as well as an initialization procedure inspired by the FURTHESTFIRST approach widely used for K-means [2]. We demonstrate that the AA model is relevant for feature extraction and dimensional reduction for a large variety of machine learning problems taken from computer vision, neuroimaging, text mining and collaborative filtering.
]]></description>
<dc:subject>archetypal-analysis machine-learning clustering rather-interesting dimension-reduction to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:19f09356d1e3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:archetypal-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1702.02808">
    <title>[1702.02808] Memetic search for overlapping topics based on a local evaluation of link communities</title>
    <dc:date>2017-02-16T11:44:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.02808</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In spite of recent advances in field delineation methods, bibliometricians still don't know the extent to which their topic detection algorithms reconstruct `ground truths', i.e. thematic structures in the scientific literature. In this paper, we demonstrate a new approach to the delineation of thematic structures that attempts to match the algorithm to theoretically derived and empirically observed properties all thematic structures have in common. We cluster citation links rather than publication nodes, use predominantly local information and search for communities of links starting from seed subgraphs in order to allow for pervasive overlaps of topics. We evaluate sets of links with a new cost function and assume that local minima in the cost landscape correspond to link communities. Because this cost landscape has many local minima we define a valid community as the community with the lowest minimum within a certain range. Since finding all valid communities is impossible for large networks, we designed a memetic algorithm that combines probabilistic evolutionary strategies with deterministic local searches. We apply our approach to a network of about 15,000 Astronomy & Astrophysics papers published 2010 and their cited sources, and to a network of about 100,000 Astronomy & Astrophysics papers (published 2003--2010) which are linked through direct citations.
]]></description>
<dc:subject>bibliometrics citation social-networks feature-extraction clustering rather-interesting academic-culture system-of-professions</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:983bef5ba6a9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bibliometrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:citation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:academic-culture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:system-of-professions"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1506.07613">
    <title>[1506.07613] Generalized Majorization-Minimization</title>
    <dc:date>2017-02-01T12:37:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1506.07613</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Non-convex optimization is ubiquitous in machine learning. The Majorization-Minimization (MM) procedure systematically optimizes non-convex functions through an iterative construction and optimization of upper bounds on the objective function. The bound at each iteration is required to \emph{touch} the objective function at the optimizer of the previous bound. We show that this touching constraint is unnecessary and overly restrictive. We generalize MM by relaxing this constraint, and propose a new framework for designing optimization algorithms, named Generalized Majorization-Minimization (G-MM). Compared to MM, G-MM is much more flexible. For instance, it can incorporate application-specific biases into the optimization procedure without changing the objective function. We derive G-MM algorithms for several latent variable models and show that they consistently outperform their MM counterparts in optimizing non-convex objectives. In particular, G-MM algorithms appear to be less sensitive to initialization.
]]></description>
<dc:subject>statistics clustering rather-interesting algorithms information-theory performance-measure nudge-targets consider:performance-measures to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7f101afbf76f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1607.06407">
    <title>[1607.06407] Small-Variance Nonparametric Clustering on the Hypersphere</title>
    <dc:date>2017-01-12T12:16:49+00:00</dc:date>
    <link>https://arxiv.org/abs/1607.06407</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Structural regularities in man-made environments reflect in the distribution of their surface normals. Describing these surface normal distributions is important in many computer vision applications, such as scene understanding, plane segmentation, and regularization of 3D reconstructions. Based on the small-variance limit of Bayesian nonparametric von-Mises-Fisher (vMF) mixture distributions, we propose two new flexible and efficient k-means-like clustering algorithms for directional data such as surface normals. The first, DP-vMF-means, is a batch clustering algorithm derived from the Dirichlet process (DP) vMF mixture. Recognizing the sequential nature of data collection in many applications, we extend this algorithm to DDP-vMF-means, which infers temporally evolving cluster structure from streaming data. Both algorithms naturally respect the geometry of directional data, which lies on the unit sphere. We demonstrate their performance on synthetic directional data and real 3D surface normals from RGB-D sensors. While our experiments focus on 3D data, both algorithms generalize to high dimensional directional data such as protein backbone configurations and semantic word vectors.
]]></description>
<dc:subject>clustering image-processing rather-interesting representation algorithms machine-learning nudge-targets consider:representation consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:726f43e3c6f4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1607.06294">
    <title>[1607.06294] Hierarchical Clustering of Asymmetric Networks</title>
    <dc:date>2017-01-10T13:15:44+00:00</dc:date>
    <link>https://arxiv.org/abs/1607.06294</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper considers networks where relationships between nodes are represented by directed dissimilarities. The goal is to study methods that, based on the dissimilarity structure, output hierarchical clusters, i.e., a family of nested partitions indexed by a connectivity parameter. Our construction of hierarchical clustering methods is built around the concept of admissible methods, which are those that abide by the axioms of value - nodes in a network with two nodes are clustered together at the maximum of the two dissimilarities between them - and transformation - when dissimilarities are reduced, the network may become more clustered but not less. Two particular methods, termed reciprocal and nonreciprocal clustering, are shown to provide upper and lower bounds in the space of admissible methods. Furthermore, alternative clustering methodologies and axioms are considered. In particular, modifying the axiom of value such that clustering in two-node networks occurs at the minimum of the two dissimilarities entails the existence of a unique admissible clustering method.
]]></description>
<dc:subject>clustering similarity algorithms rather-interesting performance-measure machine-learning representation to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ee1f3982a3f2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:similarity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.05579">
    <title>[1611.05579] Bus Stops Location and Bus Route Planning Using Mean Shift Clustering and Ant Colony in West Jakarta</title>
    <dc:date>2016-12-06T14:32:36+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.05579</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Traffic Jam has been a daily problem for people in Jakarta which is one of the busiest city in Indonesia up until now. Even though the official government has tried to reduce the impact of traffic issues by developing a new public transportation which takes up a lot of resources and time, it failed to diminish the problem. The actual concern to this problem actually lies in how people move between places in Jakarta where they always using their own vehicle like cars, and motorcycles that fill most of the street in Jakarta. Among much other public transportations that roams the street of Jakarta, Buses is believed to be an efficient transportation that can move many people at once. However, the location of the bus stop is now have moved to the middle of the main road, and it is too far for the nearby residence to access to it. This paper proposes an optimal location of optimal bus stops in West Jakarta that is experimentally proven to have a maximal distance of 350 m. The optimal location is estimated by means of mean shift clustering method while the optimal routes are calculated using Ant Colony algorithm. The bus stops locations rate of error is 0.07% with overall route area of 32 km. Based on our experiments, we believe our proposed bus stop plan can be an interesting alternative to reduce traffic congestion in West Jakarta.
]]></description>
<dc:subject>public-policy operations-research algorithms clustering rather-interesting to-write-about nudge-targets consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0bb4d5cb34c9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:public-policy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1512.06809">
    <title>[1512.06809] On the classification problem for Poisson Point Processes</title>
    <dc:date>2016-12-04T14:21:49+00:00</dc:date>
    <link>https://arxiv.org/abs/1512.06809</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We study the binary classification problem for Poisson point processes, which are allowed to take values in a general metric space. The problem is tackled in two different ways: estimating nonparametricaly the intensity functions of the processes (and then plugged into a deterministic formula which expresses the regression function in terms of the intensities), and performing the classical k nearest neighbor rule by introducing a suitable distance between patterns of points. In the first approach we prove the consistency of the estimated intensity so that the rule turns out to be also consistent. For the k-NN classifier, we prove that the regression function fulfils the so called "Besicovitch condition", usually required for the consistency of the classical classification rules. The theoretical findings are illustrated on simulated data, where in one case the k-NN rule outperforms the first approach.
]]></description>
<dc:subject>representation statistics clustering metrics rather-interesting algorithms nudge-targets consider:looking-to-see to-write-about consider:simulation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:eff132087e7c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:simulation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1607.06318">
    <title>[1607.06318] Hierarchical Manifold Clustering on Diffusion Maps for Connectomics (MIT 18.S096 final project)</title>
    <dc:date>2016-11-20T13:27:26+00:00</dc:date>
    <link>https://arxiv.org/abs/1607.06318</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we introduce a novel algorithm for segmentation of imperfect boundary probability maps (BPM) in connectomics. Our algorithm can be a considered as an extension of spectral clustering. Instead of clustering the diffusion maps with traditional clustering algorithms, we learn the manifold and compute an estimate of the minimum normalized cut. We proceed by divide and conquer. We also introduce a novel criterion for determining if further splits are necessary in a component based on it's topological properties. Our algorithm complements the currently popular agglomeration approaches in connectomics, which overlook the geometrical aspects of this segmentation problem.
]]></description>
<dc:subject>image-segmentation machine-learning rather-interesting clustering image-analysis inference neural-networks tomography nudge-targets to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d562a47dc636/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tomography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1605.00562">
    <title>[1605.00562] Persistent homology of time-dependent functional networks constructed from coupled time series</title>
    <dc:date>2016-09-29T11:16:39+00:00</dc:date>
    <link>http://arxiv.org/abs/1605.00562</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We use topological data analysis to study "functional networks" that we construct from time-series data from both experimental and synthetic sources. We use persistent homology in combination with a weight rank clique filtration to gain insights into these functional networks, and we use persistence landscapes to interpret our results. Our first example consists of biological data in the form of functional magnetic resonance imaging (fMRI) data that was acquired from human subjects during a simple motor-learning task. Our second example uses time-series output from networks of coupled Kuramoto oscillators. With these examples, we demonstrate that (1) using persistent homology to study functional networks provides fascinating insights into their properties and (2) the position of the features in a filtration can play a more vital role than persistence in the interpretation of topological features, even though conventionally the latter is used to distinguish between signal and noise. We find that persistent homology can detect differences in synchronization patterns in our data sets over time, giving insight both on changes in community structure in the networks and on increased synchronization between brain regions that form loops in a functional network during motor learning. For the motor-learning data, persistence landscapes also reveal that on average the majority of changes in the network loops takes place on the second of three days of the learning process.
]]></description>
<dc:subject>nonlinear-dynamics time-series approximation clustering rather-interesting feature-extraction nudge-targets consider:performance-measures consider:representation reminds-me-of-Wim's-paper</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a98938472c1d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reminds-me-of-Wim's-paper"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1511.05933">
    <title>[1511.05933] Towards O(1) Seeding of K-Means</title>
    <dc:date>2016-08-15T12:11:46+00:00</dc:date>
    <link>http://arxiv.org/abs/1511.05933</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[K-means is one of the most widely used algorithms for clustering in Data Mining applications, which attempts to minimize the sum of square of Euclidean distance of the points in the clusters from the respective means of the clusters. The simplicity and scalability of K-means makes it very appealing. However, K-means suffers from local minima problem, and comes with no guarantee to converge to the optimal cost. K-means++ tries to address the problem by seeding the means using a distance based sampling scheme. However, seeding the means in K-means++ needs O(K) passes through the entire dataset. This could be very costly in large amount of dataset. Here we propose a method of seeding initial means based on factorizations of higher order moments for bounded data. Our method takes O(1) passes through the entire dataset to extract the initial set of means, and its final cost can be proven to be within O(K‾‾√) of the optimal cost. We demonstrate the performance of our algorithm in comparison with the existing algorithms on various benchmark datasets.]]></description>
<dc:subject>data-mining clustering algorithms computational-complexity initialization horse-races nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:92e73486acf8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:initialization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1605.07030">
    <title>[1605.07030] Isotropic Dynamic Hierarchical Clustering</title>
    <dc:date>2016-07-24T01:43:02+00:00</dc:date>
    <link>http://arxiv.org/abs/1605.07030</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We face a need of discovering a pattern in locations of a great number of points in a high-dimensional space. Goal is to group the close points together. We are interested in a hierarchical structure, like a B-tree. B-Trees are hierarchical, balanced, and they can be constructed dynamically. B-Tree approach allows to determine the structure without any supervised learning or a priori knowlwdge. The space is Euclidean and isotropic. Unfortunately, there are no B-Tree implementations processing indices in a symmetrical and isotropical way. Some implementations are based on constructing compound asymmetrical indices from point coordinates; and the others split the nodes along the coordinate hyper-planes. We need to process tens of millions of points in a thousand-dimensional space. The application has to be scalable. Ideally, a cluster should be an ellipsoid, but it would require to store O(n2) ellipse axes. So, we are using multi-dimensional balls defined by the centers and radii. Calculation of statistical values like the mean and the average deviation, can be done in an incremental way. While adding a point to a tree, the statistical values for nodes recalculated in O(1) time. We support both, brute force O(2n) and greedy O(n2) split algorithms. Statistical and aggregated node information also allows to manipulate (to search, to delete) aggregated sets of closely located points. Hierarchical information retrieval. When searching, the user is provided with the highest appropriate nodes in the tree hierarchy, with the most important clusters emerging in the hierarchy automatically. Then, if interested, the user may navigate down the tree to more specific points. The system is implemented as a library of Java classes representing Points, Sets of points with aggregated statistical information, B-tree, and Nodes with a support of serialization and storage in a MySQL database.
]]></description>
<dc:subject>clustering data-analysis dimension-reduction algorithms machine-learning statistics nudge-targets performance-measure rather-interesting consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6468b8561d6b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1606.00985">
    <title>[1606.00985] A Graph-Based Semi-Supervised k Nearest-Neighbor Method for Nonlinear Manifold Distributed Data Classification</title>
    <dc:date>2016-06-25T20:56:43+00:00</dc:date>
    <link>http://arxiv.org/abs/1606.00985</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[k Nearest Neighbors (kNN) is one of the most widely used supervised learning algorithms to classify Gaussian distributed data, but it does not achieve good results when it is applied to nonlinear manifold distributed data, especially when a very limited amount of labeled samples are available. In this paper, we propose a new graph-based kNN algorithm which can effectively handle both Gaussian distributed data and nonlinear manifold distributed data. To achieve this goal, we first propose a constrained Tired Random Walk (TRW) by constructing an R-level nearest-neighbor strengthened tree over the graph, and then compute a TRW matrix for similarity measurement purposes. After this, the nearest neighbors are identified according to the TRW matrix and the class label of a query point is determined by the sum of all the TRW weights of its nearest neighbors. To deal with online situations, we also propose a new algorithm to handle sequential samples based a local neighborhood reconstruction. Comparison experiments are conducted on both synthetic data sets and real-world data sets to demonstrate the validity of the proposed new kNN algorithm and its improvements to other version of kNN algorithms. Given the widespread appearance of manifold structures in real-world problems and the popularity of the traditional kNN algorithm, the proposed manifold version kNN shows promising potential for classifying manifold-distributed data.]]></description>
<dc:subject>machine-learning clustering supervised-learning algorithms nudge-targets consider:adopting-this-maneuver</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:19d7c6b11793/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:supervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:adopting-this-maneuver"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1602.02514">
    <title>[1602.02514] Fast k-means with accurate bounds</title>
    <dc:date>2016-05-09T12:29:04+00:00</dc:date>
    <link>http://arxiv.org/abs/1602.02514</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose a novel accelerated exact k-means algorithm, which performs better than the current state-of-the-art low-dimensional algorithm in 18 of 22 experiments, running up to 3 times faster. We also propose a general improvement of existing state-of-the-art accelerated exact k-means algorithms through better estimates of the distance bounds used to reduce the number of distance calculations, and get a speedup in 36 of 44 experiments, up to 1.8 times faster. 
We have conducted experiments with our own implementations of existing methods to ensure homogeneous evaluation of performance, and we show that our implementations perform as well or better than existing available implementations. Finally, we propose simplified variants of standard approaches and show that they are faster than their fully-fledged counterparts in 59 of 62 experiments.
]]></description>
<dc:subject>machine-learning clustering algorithms horse-races computational-complexity rather-interesting nudge-targets consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:88c0c52b9797/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://papers.nips.cc/paper/5991-differentially-private-subspace-clustering">
    <title>Differentially private subspace clustering</title>
    <dc:date>2016-05-08T11:32:35+00:00</dc:date>
    <link>https://papers.nips.cc/paper/5991-differentially-private-subspace-clustering</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Subspace clustering is an unsupervised learning problem that aims at grouping data points into multiple clusters'' so that data points in a single cluster lie approximately on a low-dimensional linear subspace. It is originally motivated by 3D motion segmentation in computer vision, but has recently been generically applied to a wide range of statistical machine learning problems, which often involves sensitive datasets about human subjects. This raises a dire concern for data privacy. In this work, we build on the framework of differential privacy'' and present two provably private subspace clustering algorithms. We demonstrate via both theory and experiments that one of the presented methods enjoys formal privacy and utility guarantees; the other one asymptotically preserves differential privacy while having good performance in practice. Along the course of the proof, we also obtain two new provable guarantees for the agnostic subspace clustering and the graph connectivity problem which might be of independent interests.

]]></description>
<dc:subject>via:arthegall clustering algorithms neural-networks approximation machine-learning nudge-targets consider:Lexicase-selection consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e22da69e84c5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:Lexicase-selection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1507.01555">
    <title>[1507.01555] Approximate Greedy Clustering and Distance Selection for Graph Metrics</title>
    <dc:date>2016-04-10T13:18:52+00:00</dc:date>
    <link>http://arxiv.org/abs/1507.01555</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[ In this paper, we consider two important problems defined on finite metric spaces, and provide efficient new algorithms and approximation schemes for these problems on inputs given as graph shortest path metrics or high-dimensional Euclidean metrics. The first of these problems is the greedy permutation (or farthest-first traversal) of a finite metric space: a permutation of the points of the space in which each point is as far as possible from all previous points. We describe randomized algorithms to find (1+ε)-approximate greedy permutations of any graph with n vertices and m edges in expected time O(ε−1(m+n)lognlog(n/ε)), and to find (1+ε)-approximate greedy permutations of points in high-dimensional Euclidean spaces in expected time O(ε−2n1+1/(1+ε)2+o(1)). Additionally we describe a deterministic algorithm to find exact greedy permutations of any graph with n vertices and treewidth O(1) in worst-case time O(n3/2logO(1)n). The second of the two problems we consider is distance selection: given k∈[(n2)], we are interested in computing the kth smallest distance in the given metric space. We show that for planar graph metrics one can approximate this distance, up to a constant factor, in near linear time.
]]></description>
<dc:subject>computational-geometry clustering approximation algorithms nudge-targets consider:classification consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0e87c38a73f0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1511.01964">
    <title>[1511.01964] Network comparison using directed graphlets</title>
    <dc:date>2016-03-26T23:17:35+00:00</dc:date>
    <link>http://arxiv.org/abs/1511.01964</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[With recent advances in high-throughput cell biology the amount of cellular biological data has grown drastically. Such data is often modeled as graphs (also called networks) and studying them can lead to new insights into molecule-level organization. A possible way to understand their structure is by analysing the smaller components that constitute them, namely network motifs and graphlets. Graphlets are particularly well suited to compare networks and to assess their level of similarity but are almost always used as small undirected graphs of up to five nodes, thus limiting their applicability in directed networks. However, a large set of interesting biological networks such as metabolic, cell signaling or transcriptional regulatory networks are intrinsically directional, and using metrics that ignore edge direction may gravely hinder information extraction. The applicability of graphlets is extended to directed networks by considering the edge direction of the graphlets. We tested our approach on a set of directed biological networks and verified that they were correctly grouped by type using directed graphlets. However, enumerating all graphlets in a large network is a computationally demanding task. Our implementation addresses this concern by using a state-of-the-art data structure, the g-trie, which is able to greatly reduce the necessary computation. We compared our tool, gtrieScanner, to other state-of-the art methods and verified that it is the fastest general tool for graphlet counting.
]]></description>
<dc:subject>graph-theory feature-construction rather-interesting clustering metrics nudge-targets algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f75c9a34232a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1505.05740">
    <title>[1505.05740] Graph edit distance : a new binary linear programming formulation</title>
    <dc:date>2016-03-14T11:59:08+00:00</dc:date>
    <link>http://arxiv.org/abs/1505.05740</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Graph edit distance (GED) is a powerful and flexible graph matching paradigm that can be used to address different tasks in structural pattern recognition, machine learning, and data mining. In this paper, some new binary linear programming formulations for computing the exact GED between two graphs are proposed. A major strength of the formulations lies in their genericity since the GED can be computed between directed or undirected fully attributed graphs (i.e. with attributes on both vertices and edges). Moreover, a relaxation of the domain constraints in the formulations provides efficient lower bound approximations of the GED. A complete experimental study comparing the proposed formulations with 4 state-of-the-art algorithms for exact and approximate graph edit distances is provided. By considering both the quality of the proposed solution and the efficiency of the algorithms as performance criteria, the results show that none of the compared methods dominates the others in the Pareto sense. As a consequence, faced to a given real-world problem, a trade-off between quality and efficiency has to be chosen w.r.t. the application constraints. In this context, this paper provides a guide that can be used to choose the appropriate method.
]]></description>
<dc:subject>graph-theory algorithms metrics edit-distance linear-programming rather-interesting clustering nudge-targets consider:implementing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:184c0c1e149c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:edit-distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:linear-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:implementing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1508.01057">
    <title>[1508.01057] On the convergence of the sparse possibilistic c-means algorithm</title>
    <dc:date>2015-12-23T12:45:17+00:00</dc:date>
    <link>http://arxiv.org/abs/1508.01057</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, a convergence proof for the recently proposed sparse possibilistic c-means (SPCM) algorithm is provided, utilizing the celebrated Zangwill convergence theorem. It is shown that the iterative sequence generated by SPCM converges to a stationary point or there exists a subsequence of it that converges to a stationary point of the cost function of the algorithm.
]]></description>
<dc:subject>clustering fuzzy machine-learning algorithms nudge-targets consider:representation stress-testing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a876ca2a75ea/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fuzzy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:stress-testing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1412.7012">
    <title>[1412.7012] Boltzmann-machine learning of prior distributions of binarized natural images</title>
    <dc:date>2015-12-21T12:06:00+00:00</dc:date>
    <link>http://arxiv.org/abs/1412.7012</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Prior distributions of binarized natural images are learned by using Boltzmann machine. We find that there emerges a structure with two sublattices in the interactions, and the nearest-neighbor and next-nearest-neighbor interactions correspondingly take two discriminative values, which reflects individual characteristics of three sets of pictures we treat. On the other hand, in a longer spacial scale, a longer-range (though still rapidly-decaying) ferromagnetic interaction commonly appear in all the cases. The characteristic length scale of the interactions is universally about up to four lattice spacing ξ≈4. These results are derived by using the mean-field method which effectively reduces the computational time required in Boltzmann machine. An improved mean-field method called the Bethe approximation also gives the same result, which reinforces the validity of our analysis and findings. Relations to criticality, frustration, and simple-cell receptive fields are also discussed.
]]></description>
<dc:subject>machine-learning approximation signal-processing neural-networks algorithms nudge-targets representation consider:incremental-representations clustering</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3677326fa331/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:signal-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:incremental-representations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1510.00012">
    <title>[1510.00012] Accelerated Discrete Distribution Clustering under Wasserstein Distance</title>
    <dc:date>2015-12-15T12:55:07+00:00</dc:date>
    <link>http://arxiv.org/abs/1510.00012</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In a variety of research areas, the bag of weighted vectors and the histogram are widely used descriptors for complex objects. Both can be expressed as discrete distributions. D2-clustering pursues the minimum total within-cluster variation for a set of discrete distributions subject to the Kantorovich-Wasserstein metric. D2-clustering has a severe scalability issue, the bottleneck being the computation of a centroid distribution that minimizes its sum of squared distances to the cluster members. In this paper, we develop three scalable optimization techniques, specifically, the subgradient descent method, ADMM, and modified Bregman ADMM, for computing the centroids of large clusters without compromising the objective function. The strengths and weaknesses of these techniques are examined through experiments; and scenarios for their respective usage are recommended. Moreover, we develop both serial and parallelized versions of the algorithms, collectively named the AD2-clustering. By experimenting with large-scale data, we demonstrate the computational efficiency of the new methods and investigate their convergence properties and numerical stability. The clustering results obtained on several datasets in different domains are highly competitive in comparison with some widely used methods' in the corresponding areas.
]]></description>
<dc:subject>clustering metrics histograms numerical-methods statistics algorithms nudge-targets consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4b3d46f72857/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:histograms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:numerical-methods"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1310.4945">
    <title>[1310.4945] A novel sparsity and clustering regularization</title>
    <dc:date>2015-12-13T14:44:28+00:00</dc:date>
    <link>http://arxiv.org/abs/1310.4945</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose a novel SPARsity and Clustering (SPARC) regularizer, which is a modified version of the previous octagonal shrinkage and clustering algorithm for regression (OSCAR), where, the proposed regularizer consists of a K-sparse constraint and a pair-wise ℓ∞ norm restricted on the K largest components in magnitude. The proposed regularizer is able to separably enforce K-sparsity and encourage the non-zeros to be equal in magnitude. Moreover, it can accurately group the features without shrinking their magnitude. In fact, SPARC is closely related to OSCAR, so that the proximity operator of the former can be efficiently computed based on that of the latter, allowing using proximal splitting algorithms to solve problems with SPARC regularization. Experiments on synthetic data and with benchmark breast cancer data show that SPARC is a competitive group-sparsity inducing regularizer for regression and classification.
]]></description>
<dc:subject>compressed-sensing signal-processing clustering algorithms nudge-targets operations-research</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b9a75e4b7b67/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:compressed-sensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:signal-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1508.04887">
    <title>[1508.04887] Multi-criteria Similarity-based Anomaly Detection using Pareto Depth Analysis</title>
    <dc:date>2015-12-13T13:13:56+00:00</dc:date>
    <link>http://arxiv.org/abs/1508.04887</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We consider the problem of identifying patterns in a data set that exhibit anomalous behavior, often referred to as anomaly detection. Similarity-based anomaly detection algorithms detect abnormally large amounts of similarity or dissimilarity, e.g.~as measured by nearest neighbor Euclidean distances between a test sample and the training samples. In many application domains there may not exist a single dissimilarity measure that captures all possible anomalous patterns. In such cases, multiple dissimilarity measures can be defined, including non-metric measures, and one can test for anomalies by scalarizing using a non-negative linear combination of them. If the relative importance of the different dissimilarity measures are not known in advance, as in many anomaly detection applications, the anomaly detection algorithm may need to be executed multiple times with different choices of weights in the linear combination. In this paper, we propose a method for similarity-based anomaly detection using a novel multi-criteria dissimilarity measure, the Pareto depth. The proposed Pareto depth analysis (PDA) anomaly detection algorithm uses the concept of Pareto optimality to detect anomalies under multiple criteria without having to run an algorithm multiple times with different choices of weights. The proposed PDA approach is provably better than using linear combinations of the criteria and shows superior performance on experiments with synthetic and real data sets.
]]></description>
<dc:subject>anomaly-detection multiobjective-optimization rather-interesting nudge-targets clustering outliers algorithms statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7617f227409b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:anomaly-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:outliers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1412.1947">
    <title>[1412.1947] A parallel sampling based clustering</title>
    <dc:date>2015-12-13T13:04:34+00:00</dc:date>
    <link>http://arxiv.org/abs/1412.1947</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The problem of automatically clustering data is an age old problem. People have created numerous algorithms to tackle this problem. The execution time of any of this algorithm grows with the number of input points and the number of cluster centers required. To reduce the number of input points we could average the points locally and use the means or the local centers as the input for clustering. However since the required number of local centers is very high, running the clustering algorithm on the entire dataset to obtain these representational points is very time consuming. To remedy this problem, in this paper we are proposing two subclustering schemes where by we subdivide the dataset into smaller sets and run the clustering algorithm on the smaller datasets to obtain the required number of datapoints to run our clustering algorithm with. As we are subdividing the given dataset, we could run clustering algorithm on each smaller piece of the dataset in parallel. We found that both parallel and serial execution of this method to be much faster than the original clustering algorithm and error in running the clustering algorithm on a reduced set to be very less.
]]></description>
<dc:subject>clustering machine-learning again nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d2100bdca0f3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:again"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1412.5902">
    <title>[1412.5902] A Physically Inspired Clustering Algorithm: to Evolve Like Particles</title>
    <dc:date>2015-12-12T11:49:43+00:00</dc:date>
    <link>http://arxiv.org/abs/1412.5902</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Clustering analysis is a method to organize raw data into categories based on a measure of similarity. It has been successfully applied to diverse fields from science to business and engineering. By endowing data points with physical meaning like particles in the physical world and then leaning their evolving tendency of moving from higher to lower potentials, data points in the proposed clustering algorithm sequentially hop to the locations of their transfer points and gather, after a few steps, at the locations of cluster centers with the locally lowest potentials, where cluster members can be easily identified. The whole clustering process is simple and efficient, and can be performed either automatically or interactively, with reliable performances on test data of diverse shapes, attributes, and dimensionalities.
]]></description>
<dc:subject>clustering algorithms metaphor nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d8161405684c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaphor"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1309.6895">
    <title>[1309.6895] A consistent and breakdown robust model-based clustering method</title>
    <dc:date>2015-11-25T12:29:00+00:00</dc:date>
    <link>http://arxiv.org/abs/1309.6895</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The robust improper maximum likelihood estimator (RIMLE) is a new method for robust multivariate clustering finding approximately Gaussian clusters. It maximizes a pseudo-likelihood defined by adding a component with improper constant density for accommodating outliers to a Gaussian mixture. A special case of the RIMLE is MLE for multivariate finite Gaussian mixture models. In this paper we give a comprehensive treatment of existence, consistency, and breakdown theory for the RIMLE. RIMLE existence is proved under non-smooth covariance matrix constraints, it is shown that these can be implemented via a computationally feasible EM-algorithm
]]></description>
<dc:subject>clustering feature-construction horse-races algorithms machine-learning statistics nudge-targets performance-space-analysis</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e98c5bc70892/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-space-analysis"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1505.03934">
    <title>[1505.03934] Textual Spatial Cosine Similarity</title>
    <dc:date>2015-11-25T12:18:20+00:00</dc:date>
    <link>http://arxiv.org/abs/1505.03934</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[When dealing with document similarity many methods exist today, like cosine similarity. More complex methods are also available based on the semantic analysis of textual information, which are computationally expensive and rarely used in the real time feeding of content as in enterprise-wide search environments. To address these real-time constraints, we developed a new measure of document similarity called Textual Spatial Cosine Similarity, which is able to detect similitude at the semantic level using word placement information contained in the document. We will see in this paper that two degenerate cases exist for this model, which coincide with Cosine Similarity on one side and with a paraphrasing detection model to the other.
]]></description>
<dc:subject>metrics text-mining natural-language-processing digital-humanities clustering nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c7046fa36d98/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1506.08977">
    <title>[1506.08977] A comparative study of divisive hierarchical clustering algorithms</title>
    <dc:date>2015-11-25T12:11:20+00:00</dc:date>
    <link>http://arxiv.org/abs/1506.08977</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A general scheme for divisive hierarchical clustering algorithms is proposed. It is made of three main steps : first a splitting procedure for the subdivision of clusters into two subclusters, second a local evaluation of the bipartitions resulting from the tentative splits and, third, a formula for determining the nodes levels of the resulting dendrogram. A number of such algorithms is given. These algorithms are compared using the Goodman-Kruskal correlation coefficient. As a global criterion it is an internal goodness-of-fit measure based on the set order induced by the hierarchy compared to the order associated to the given dissimilarities. Applied to a hundred of random data tables, these comparisons are in favor of two methods based on unusual ratio-type formulas for the splitting procedures, namely the Silhouette criterion and Dunn's criterion. These two criteria take into account both the within cluster and the between cluster mean dissimilarity. In general the results of these two algorithms are better than the classical Agglomerative Average Link method.
]]></description>
<dc:subject>clustering algorithms generalization rather-interesting nudge-targets consider:ontology</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3b4357300b93/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generalization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:ontology"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>